def pca_prediction(prefix, components, outfile, model):
o = outPutMedia(outfile + '.pdf')
x = components
variance = []
for c in components:
variance.append(pca_pipeline(prefix, c, model))
result = '\n'.join([str(k) + ',' + str(v) for k, v in zip(x, variance)])
open(outfile + '.csv', 'w').write(result)
plt.plot(x, variance, 'ro-', linewidth=2)
plt.title('principle number vs variance explained')
plt.xlabel('Number of principle components')
plt.ylabel('Explained variance')
o.write(None)
o.close()
def plotVarianceExplained(prefix, components, outfile):
o = outPutMedia(outfile + '.pdf')
x = np.arange(components) + 1
variance = np.arange(components)
for c in range(components):
variance[c] = drive(prefix, x[c])
result = '\n'.join([str(k) + ',' + str(v) for k, v in zip(x, variance)])
open(outfile + '.csv', 'w').write(result)
plt.plot(x, variance, 'ro-', linewidth=2)
plt.title('principle number vs variance explained')
plt.xlabel('Number of principle components')
plt.ylabel('Explained variance')
o.write(None)
o.close()
def plotVarianceExplained(prefix,components,outfile):
o = outPutMedia(outfile + '.pdf')
x = np.arange(components) + 1
variance = np.arange(components)
for c in range(components):
variance[c] = drive(prefix,x[c])
result = '\n'.join([str(k) + ',' + str(v) for k,v in zip(x,variance)])
open(outfile + '.csv','w').write(result)
plt.plot(x,variance,'ro-',linewidth = 2)
plt.title('principle number vs variance explained')
plt.xlabel('Number of principle components')
plt.ylabel('Explained variance')
o.write(None)
o.close()
def pca_prediction(prefix,components,outfile,model):
o = outPutMedia(outfile + '.pdf')
x = components
variance = []
for c in components:
variance.append(pca_pipeline(prefix,c,model))
result = '\n'.join([str(k) + ',' + str(v) for k,v in zip(x,variance)])
open(outfile + '.csv','w').write(result)
plt.plot(x,variance,'ro-',linewidth = 2)
plt.title('principle number vs variance explained')
plt.xlabel('Number of principle components')
plt.ylabel('Explained variance')
o.write(None)
o.close()
def screePlot(filename,S):
o = outPutMedia(filename)
eigvals = S**2/np.cumsum(S)[-1]
eigvals2 = S**2/np.sum(S)
assert (eigvals == eigvals2).all()
x = np.arange(len(S)) + 1
print(len(x))
plt.plot(x,eigvals,'ro-',linewidth = 2)
plt.title('Scree Plot')
plt.xlabel('Principle Component')
plt.ylabel('Eigenvalue')
leg = plt.legend(['Eigenvalues from Bagofword'],loc='best',borderpad=0.3,shadow=False,markerscale = 0.4)
leg.get_frame().set_alpha(0.4)
o.write(None)
o.close()
def screePlot(filename, S):
o = outPutMedia(filename)
eigvals = S**2 / np.cumsum(S)[-1]
eigvals2 = S**2 / np.sum(S)
assert (eigvals == eigvals2).all()
x = np.arange(len(S)) + 1
print(len(x))
plt.plot(x, eigvals, 'ro-', linewidth=2)
plt.title('Scree Plot')
plt.xlabel('Principle Component')
plt.ylabel('Eigenvalue')
leg = plt.legend(['Eigenvalues from Bagofword'],
loc='best',
borderpad=0.3,
shadow=False,
markerscale=0.4)
leg.get_frame().set_alpha(0.4)
o.write(None)
o.close()
